Systems and Methods for Finger Pose Estimation on Touchscreen Devices

1. A computer-implemented method performed in a computerized system comprising a central processing unit, a touch-sensitive display device, a memory and a camera, the computer-implemented method comprising: a. using the touch-sensitive display device to detect a tactile event; b. using the camera to capture an image of an area proximal to the surface of the touch-sensitive display device, wherein the camera is a depth-imaging camera and wherein a signal from the camera comprises image information and depth information; c. using the touch-sensitive display device to determine a contact point of an object and the touch-sensitive display device, the contact point associated with the tactile event, wherein the touch-sensitive display device is separate and distinct from the camera; and d. responsive to the detection of the tactile event, using the central processing unit to determine information on a pose of the object based on the captured image and the determined contact point.

2. The computer-implemented method of claim 1 , wherein the camera is positioned on the same side relative to a surface of the touch-sensitive display device as the object contacting the touch-sensitive display device.

3. The computer-implemented method of claim 1 , wherein in d. determining the information on the pose of the object comprises obtaining a point cloud from the captured image, the point cloud comprising spatial information associated with the object.

4. The computer-implemented method of claim 3 , wherein in d. determining the information on the pose of the object comprises fitting the point cloud with a three-dimensional model.

5. The computer-implemented method of claim 4 , wherein the three-dimensional model is a cylindrical model.

6. The computer-implemented method of claim 3 , further comprising subsampling the point cloud.

7. The computer-implemented method of claim 1 , wherein in c. a plurality of contact points of a plurality of objects and the touch-sensitive display device are determined and wherein in d. information on the pose of the plurality of objects is determined based on the captured image and the plurality of contact points.

8. The computer-implemented method of claim 1 , wherein in b. a plurality of images are captured by a plurality of cameras and wherein in d. information on the pose of the object is determined based on the captured plurality of images and the contact point.

9. The computer-implemented method of claim 8 , further comprising calibrating the plurality of cameras to determine a transformation from local coordinates of each of the plurality of cameras to a unified coordinate system.

10. The computer-implemented method of claim 1 , wherein the camera is positioned such that the touch-sensitive display device is within a field of view of the camera.

11. The computer-implemented method of claim 1 , wherein the determined pose information comprises tilt angle and rotation angle of the object.

12. The computer-implemented method of claim 1 , further comprising transmitting the determined pose information to an application program.

13. The computer-implemented method of claim 1 , further comprising displaying a graphical user interface on the touch-sensitive display device, the graphical user interface comprising a widget, wherein the tactile event is directed to the widget.

14. A non-transitory computer-readable medium embodying a set of computer-executable instructions, which, when executed in a computerized system comprising a central processing unit, a touch-sensitive display device, a memory and a camera, cause the computerized system to perform a method comprising: a. using the touch-sensitive display device to detect a tactile event; b. using the camera for capturing an image of an area proximal to the surface of the touch-sensitive display device, wherein the camera is a depth-imaging camera and wherein a signal from the camera comprises image information and depth information; c. using the touch-sensitive display device to determine a contact point of an object and the touch-sensitive display device, the contact point associated with the tactile event; and d. responsive to the detection of the tactile event, using the central processing unit to determine information on a pose of the object based on the captured image and the determined contact point.

15. The non-transitory computer-readable medium of claim 14 , wherein the camera is positioned on the same side relative to a surface of the touch-sensitive display device as the object contacting the touch-sensitive display device.

16. The non-transitory computer-readable medium of claim 14 , wherein in d. determining the information on the pose of the object comprises obtaining a point cloud from the captured image, the point cloud comprising spatial information associated with the object.

17. The non-transitory computer-readable medium of claim 16 , wherein in d. determining the information on the pose of the object comprises fitting the point cloud with a three-dimensional model.

18. The non-transitory computer-readable medium of claim 17 , wherein the three-dimensional model is a cylindrical model.

19. The non-transitory computer-readable medium of claim 16 , wherein the method further comprises subsampling the point cloud.

20. A computerized system comprising: a. a touch-sensitive display device configured to detect a tactile event and to determine a contact point of an object and the touch-sensitive display device, the contact point associated with the tactile event; b. a depth-imaging camera, separate and distinct from the touch-sensitive display device, configured to capture an image of an area proximal to the surface of the touch-sensitive display device, wherein a signal from the camera comprises image information and depth information; and c. a central processing unit configured, in response to the detection of the tactile event, to determine information on a pose of the object based on the captured image and the determined contact point.